© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40973
    Prev
    Next
    INDEX
    Explanations

    hair bleach and blonde

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron is triggered by mentions of bleaching or bleach-related chemical processing terms.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Although
    -2.44
     But
    -2.30
     Perhaps
    -2.19
     Originally
    -2.14
     Unless
    -2.13
    ("%.
    -2.11
    觥
    -2.11
     Aside
    -2.11
    .’
    -2.11
     Despite
    -2.11
    POSITIVE LOGITS
    ↵
    2.89
    蠖
    2.14
     tomando
    2.06
    by
    2.02
    those
    2.00
    ᠁
    1.98
     vijf
    1.98
    '
    1.91
    0
    1.91
    some
    1.88
    Activations Density 0.005%

    No Known Activations